Title :
Moment filters for high precision computation of focus and stereo
Author :
Xiong, Yalin ; Shafer, Steven A.
Author_Institution :
Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
Many low level visual computation problems such as focus, stereo, etc. can be formulated as problems of extracting one or more parameters of a non-stationary transformation between two images. Because of the non-stationary nature, finite-width windows are widely used in various algorithms to extract spatially local information from images. While the choice of window width has a very profound impact on the quality of results of algorithms, there has been no quantitative way to measure or eliminate the negative effects of finite width windows. To address this problem, we introduce a new set of filters, moment filters. Due to their recursiveness in the Fourier and spatial domains, these filters allow the effects of finite-width windows and fore-shortening to be explicitly analyzed and eliminated
Keywords :
computer vision; convolution; filtering theory; optical focusing; spatial filters; stereo image processing; Fourier domains; computer vision; finite-width windows; focus; moment filters; non-stationary transformation; recursiveness; spatial domains; spatially local information extraction; stereo image processing; Band pass filters; Filtering theory; Focusing; Gabor filters; Image analysis; Information analysis; Parameter estimation; Passband; Polynomials; Robots;
Conference_Titel :
Intelligent Robots and Systems 95. 'Human Robot Interaction and Cooperative Robots', Proceedings. 1995 IEEE/RSJ International Conference on
Conference_Location :
Pittsburgh, PA
Print_ISBN :
0-8186-7108-4
DOI :
10.1109/IROS.1995.525870